# Offline Reinforcement Learning on 1T10S Hopper (Medium-Expert) Source: [Offline Reinforcement Learning on 1T10S Hopper (Medium-Expert)]() Collection index: [llms.txt]() Data updated: 2026-03-04T14:55:28.971Z Evaluation of Offline Reinforcement Learning performance on the 1T10S Hopper environment using the Medium-Expert configuration, measured by Score. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Offline Reinforcement Learning | | Dataset (including any stated split) | 1T10S Hopper (Medium-Expert) | | Metric | Score | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 26 of 26 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | Score | Result date | Report paper | | --- | --- | --- | --- | | D-BCQ | 111.587 | Not recorded | 68fa757c1e209131cea684c9 | | D-BCQ | 110.014 | Not recorded | 68fa757c1e209131cea684c9 | | H2O | 109.457 | Not recorded | 68fa757c1e209131cea684c9 | | BCQ | 109.367 | Not recorded | 68fa757c1e209131cea684c9 | | H2O | 108.872 | Not recorded | 68fa757c1e209131cea684c9 | | BCQ | 108.639 | Not recorded | 68fa757c1e209131cea684c9 | | IGDF | 105.465 | Not recorded | 68fa757c1e209131cea684c9 | | IGDF | 99.057 | Not recorded | 68fa757c1e209131cea684c9 | | D-CQL | 94.128 | Not recorded | 68fa757c1e209131cea684c9 | | D-AWR | 78.262 | Not recorded | 68fa757c1e209131cea684c9 | | AWR | 74.708 | Not recorded | 68fa757c1e209131cea684c9 | | DFDT | 74.306 | Not recorded | 68fa757c1e209131cea684c9 | | CQL | 72.512 | Not recorded | 68fa757c1e209131cea684c9 | | D-CQL | 72.149 | Not recorded | 68fa757c1e209131cea684c9 | | DFDT | 70.703 | Not recorded | 68fa757c1e209131cea684c9 | | CQL | 70.467 | Not recorded | 68fa757c1e209131cea684c9 | | D-AWR | 60.952 | Not recorded | 68fa757c1e209131cea684c9 | | AWR | 57.595 | Not recorded | 68fa757c1e209131cea684c9 | | BEAR | 39.031 | Not recorded | 68fa757c1e209131cea684c9 | | D-BEAR | 33.052 | Not recorded | 68fa757c1e209131cea684c9 | | D-MOPO | 32.589 | Not recorded | 68fa757c1e209131cea684c9 | | D-BEAR | 31.09 | Not recorded | 68fa757c1e209131cea684c9 | | MOPO | 30.541 | Not recorded | 68fa757c1e209131cea684c9 | | D-MOPO | 30.54 | Not recorded | 68fa757c1e209131cea684c9 | | MOPO | 30.537 | Not recorded | 68fa757c1e209131cea684c9 | | BEAR | 22.934 | Not recorded | 68fa757c1e209131cea684c9 | ### D-BCQ Score: 111.587. Result ID: 69a847db6dbb7075b94f3580. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### D-BCQ Score: 110.014. Result ID: 69a847db6dbb7075b94f3573. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### H2O Score: 109.457. Result ID: 69a847db6dbb7075b94f3584. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### BCQ Score: 109.367. Result ID: 69a847db6dbb7075b94f356e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### H2O Score: 108.872. Result ID: 69a847db6dbb7075b94f3577. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### BCQ Score: 108.639. Result ID: 69a847db6dbb7075b94f357b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### IGDF Score: 105.465. Result ID: 69a847db6dbb7075b94f3578. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### IGDF Score: 99.057. Result ID: 69a847db6dbb7075b94f3585. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### D-CQL Score: 94.128. Result ID: 69a847db6dbb7075b94f3581. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### D-AWR Score: 78.262. Result ID: 69a847db6dbb7075b94f3572. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### AWR Score: 74.708. Result ID: 69a847db6dbb7075b94f357a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### DFDT Score: 74.306. Result ID: 69a847db6dbb7075b94f3583. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### CQL Score: 72.512. Result ID: 69a847db6dbb7075b94f357c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### D-CQL Score: 72.149. Result ID: 69a847db6dbb7075b94f3574. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### DFDT Score: 70.703. Result ID: 69a847db6dbb7075b94f3576. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### CQL Score: 70.467. Result ID: 69a847db6dbb7075b94f356f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### D-AWR Score: 60.952. Result ID: 69a847db6dbb7075b94f357f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### AWR Score: 57.595. Result ID: 69a847db6dbb7075b94f356d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### BEAR Score: 39.031. Result ID: 69a847db6dbb7075b94f3579. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### D-BEAR Score: 33.052. Result ID: 69a847db6dbb7075b94f357e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### D-MOPO Score: 32.589. Result ID: 69a847db6dbb7075b94f3582. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### D-BEAR Score: 31.09. Result ID: 69a847db6dbb7075b94f3571. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### MOPO Score: 30.541. Result ID: 69a847db6dbb7075b94f3570. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### D-MOPO Score: 30.54. Result ID: 69a847db6dbb7075b94f3575. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. ### MOPO Score: 30.537. Result ID: 69a847db6dbb7075b94f357d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"JointNoise"}. This record does not assert independent reproduction. ### BEAR Score: 22.934. Result ID: 69a847db6dbb7075b94f356c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distribution Shift":"BodyMass"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.